arXiv subjects

Byeongseon Park

Publications and source records attributed to Byeongseon Park.

5 recordsLinked to original sources

arXiv2026

Decomposition of Solar Wind Velocity Distribution Functions with Orthogonal Polynomials

We present a framework for decomposing solar-wind velocity distribution functions (VDFs) using orthogonal polynomial bases. We aim to establish a practical procedure for applying polynomial decompositions to in-situ spacecraft VDFs and to clarify how the resulting spectra of expansion-coefficient power can be used for noise reduction, VDF reconstruction, and diagnostics of velocity-space structure. The method represents measured VDF structure with Hermite-Hermite and Hermite-Laguerre expansions, providing a nonparametric description of departures from Maxwellians, such as anisotropy, skewness, beams, and suprathermal tails. Expansion coefficients are estimated by Gaussian-weighted quadrature after interpolation of measured distributions onto polynomial nodes. We demonstrate several applications of polynomial decomposition to Solar Orbiter, Parker Solar Probe, and Magnetospheric Multiscale 1 measurements, including noise identification through high-order spectral flattening, noise-reduced VDF reconstruction, and characterization of VDF-structure variations under different plasma conditions, e.g., turbulent solar-wind streams and shocks. For instance, noise-reduced reconstructed VDFs can provide smoother estimates of distinct ion populations and VDF gradients. Examples from solar-wind streams and collisionless-shock crossings further show that the resulting spectra respond to changes in parallel and perpendicular VDF structure, illustrating their potential for comparing kinetic modifications under different plasma conditions. Overall, orthogonal-polynomial decomposition provides a bridge between measured particle distributions and kinetic plasma physics by converting complex VDF morphology into quantitative velocity-space spectra.

astro-ph.SR↗

arXiv2025

Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-Tuning

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific performances because conventional reward functions are mainly aimed at enhancing the quality across the whole generated video sequence, such as aesthetic appeal and overall consistency. Notably, the temporal consistency of the generated video often suffers when applying previous approaches to image-to-video (I2V) generation tasks. To address this limitation, we propose Video Consistency Distance (VCD), a novel metric designed to enhance temporal consistency, and fine-tune a model with the reward-based fine-tuning framework. To achieve coherent temporal consistency relative to a conditioning image, VCD is defined in the frequency space of video frame features to capture frame information effectively through frequency-domain analysis. Experimental results across multiple I2V datasets demonstrate that fine-tuning a video generation model with VCD significantly enhances temporal consistency without degrading other performance compared to the previous method.

cs.CV↗

arXiv2025

Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning

We propose a model to obtain phonemic and prosodic labels of speech that are coherent with graphemes. Unlike previous methods that simply fine-tune a pre-trained ASR model with the labels, the proposed model conditions the label generation on corresponding graphemes by two methods: 1) Add implicit grapheme conditioning through prompt encoder using pre-trained BERT features. 2) Explicitly prune the label hypotheses inconsistent with the grapheme during inference. These methods enable obtaining parallel data of speech, the labels, and graphemes, which is applicable to various downstream tasks such as text-to-speech and accent estimation from text. Experiments showed that the proposed method significantly improved the consistency between graphemes and the predicted labels. Further, experiments on accent estimation task confirmed that the created parallel data by the proposed method effectively improve the estimation accuracy.

cs.SD↗

arXiv2024

Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data

This paper proposes an audio-conditioned phonemic and prosodic annotation model for building text-to-speech (TTS) datasets from unlabeled speech samples. For creating a TTS dataset that consists of label-speech paired data, the proposed annotation model leverages an automatic speech recognition (ASR) model to obtain phonemic and prosodic labels from unlabeled speech samples. By fine-tuning a large-scale pre-trained ASR model, we can construct the annotation model using a limited amount of label-speech paired data within an existing TTS dataset. To alleviate the shortage of label-speech paired data for training the annotation model, we generate pseudo label-speech paired data using text-only corpora and an auxiliary TTS model. This TTS model is also trained with the existing TTS dataset. Experimental results show that the TTS model trained with the dataset created by the proposed annotation method can synthesize speech as naturally as the one trained with a fully-labeled dataset.

eess.AS↗

arXiv2021

Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis

We propose a novel phrase break prediction method that combines implicit features extracted from a pre-trained large language model, a.k.a BERT, and explicit features extracted from BiLSTM with linguistic features. In conventional BiLSTM based methods, word representations and/or sentence representations are used as independent components. The proposed method takes account of both representations to extract the latent semantics, which cannot be captured by previous methods. The objective evaluation results show that the proposed method obtains an absolute improvement of 3.2 points for the F1 score compared with BiLSTM-based conventional methods using linguistic features. Moreover, the perceptual listening test results verify that a TTS system that applied our proposed method achieved a mean opinion score of 4.39 in prosody naturalness, which is highly competitive with the score of 4.37 for synthesized speech with ground-truth phrase breaks.

eess.AS↗